Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4551 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5212. Min Range: -2.5212

Max Act: 2.5174. Min Act: -0.0000

Data Index: 197948 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 2.5212. Min Range: -2.5212

Max Act: 2.5212. Min Act: -0.0000

Data Index: 938359 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 2.5212. Min Range: -2.5212

Max Act: 2.3060. Min Act: -0.0000

Data Index: 223956 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 2.5212. Min Range: -2.5212

Max Act: 2.2100. Min Act: -0.0000

Data Index: 565985 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 2.5212. Min Range: -2.5212

Max Act: 2.1912. Min Act: -0.0000

Data Index: 1161147 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.9416. Min Act: -0.0000

Data Index: 443568 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.6410. Min Act: -0.0000

Data Index: 683980 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.9960. Min Act: -0.0000

Data Index: 473861 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.8749. Min Act: -0.0000

Data Index: 1216528 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.9555. Min Act: -0.0000

Data Index: 319791 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 2.5212. Min Range: -2.5212

Max Act: 2.0641. Min Act: -0.0000

Data Index: 744761 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.9317. Min Act: -0.0000

Data Index: 1349508 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.9385. Min Act: -0.0000

Data Index: 1133529 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.9135. Min Act: -0.0000

Data Index: 1097306 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.8930. Min Act: -0.0000

Data Index: 159774 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.9101. Min Act: -0.0000

Data Index: 216172 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.8993. Min Act: -0.0000

Data Index: 594416 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.7399. Min Act: -0.0000

Data Index: 1230287 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.7073. Min Act: -0.0000

Data Index: 1356024 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 2.5212. Min Range: -2.5212

Max Act: 1.8121. Min Act: -0.0000

Data Index: 1165851 (C4 (Web Text))

Max Activating Token Index: 57